US 12,105,720 B2
Machine learning to infer title levels across entities
Huichao Xue, Santa Clara, CA (US); Xiaoqing Wang, San Jose, CA (US); and Chao Wang, San Jose, CA (US)
Assigned to Microsoft Technology Licensing, LLC, Redmond, WA (US)
Filed by Microsoft Technology Licensing, LLC, Redmond, WA (US)
Filed on Feb. 3, 2022, as Appl. No. 17/592,128.
Prior Publication US 2023/0281207 A1, Sep. 7, 2023
Int. Cl. G06F 16/2457 (2019.01)
CPC G06F 16/24578 (2019.01) 18 Claims
OG exemplary drawing
 
1. A system comprising:
a memory; and
a computer-readable medium having instructions stored thereon, which, when executed by a processor, cause the system to perform operations comprising:
accessing training data including information about job transitions of users, a job transition including information about an employing entity and a job title for a source job and an employing entity and job title for a target job, and a duration of time between a start of the source job and a start of the target job;
transforming the training data so that vectors in the training data correspond uniquely to transitions in the training data;
passing the vectors in the training data to a machine learning algorithm to train an embedding model, the training comprising calculating velocities for the vectors and using the velocities to train an embedding model by iteratively altering embeddings of the embedding model until a loss function is minimized, a velocity being equal to, for a given transition, a seniority score for an employing entity and a job title for a target job of the given transition minus a seniority score for an employing entity and job title for a source job of the given transition, divided by the duration of time for the given transition,
the trained embedding model configured to predict a seniority score for a first job having a first employing entity and a first job title.